Learning with Refutation

نویسندگان

چکیده

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning with Refutation

In their pioneering work, Mukouchi and Arikawa modeled a learning situation in which the learner is expected to refute texts which are not representative of L, the class of languages being identified. Lange and Watson extended this model to consider justified refutation in which the learner is expected to refute texts only if it contains a finite sample unrepresentative of the class L. Both the...

متن کامل

On Learning versus Refutation

Building on the work of Daniely et al. (STOC 2014, COLT 2016), we study the connection between computationally efficient PAC learning and refutation of constraint satisfaction problems. Specifically, we prove that for every concept class P, PAC-learning P is polynomially equivalent to “random-right-hand-side-refuting” (“RRHS-refuting”) a dual class P∗, where RRHS-refutation of a class Q refers ...

متن کامل

On Learning vs. Refutation

Building on the work of Daniely et al. (STOC 2014, COLT 2016), we study the connection between computationally efficient PAC learning and refutation of constraint satisfaction problems. Specifically, we prove that for every concept class P, PAC-learning P is polynomially equivalent to “random-right-hand-side-refuting” (“RRHS-refuting”) a dual class P∗, where RRHS-refutation of a class Q refers ...

متن کامل

Negation As Refutation

A refutation mechanism is introduced into logic programming, dual to the usual proof mechanism; then negation is treated via refutation. A four-valued logic is appropriate for the semantics: true, false, neither, both. Inconsistent programs are allowed, but inconsistencies remain localized. The four-valued logic is a well-known one, due to Belnap, and is the simplest example of Ginsberg’s bilat...

متن کامل

Fast DQBF Refutation

Dependency Quantified Boolean Formulas (DQBF) extend QBF with Henkin quantifiers, which allow for non-linear dependencies between the quantified variables. This extension is useful in verification problems for incomplete designs, such as the partial equivalence checking (PEC) problem, where a partial circuit, with some parts left open as “black boxes”, is compared against a full circuit. The PE...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of Computer and System Sciences

سال: 1998

ISSN: 0022-0000

DOI: 10.1006/jcss.1998.1591